Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    em dashes

    oai_token-act-pair · gemini-2.0-flash

    dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     —
    -1.50
    —
    -1.39
    "—
    -1.24
    )—
    -1.23
    ”—
    -1.16
     ——
    -1.09
    —"
    -1.08
    ——
    -1.05
    —(
    -0.98
     —,
    -0.98
    POSITIVE LOGITS
    ThroughAttribute
    0.63
     Kit
    0.47
     para
    0.47
     kit
    0.47
    سب
    0.45
     ´
    0.45
    ɵɵ
    0.45
     rast
    0.44
     thẩm
    0.44
     SPECIFIC
    0.44
    Act Density 1.844%

    No Known Activations